The innovation, which narrates written texts in a natural way, generates new, realistically sounding, not yet existing voices. Speech properties like speed and pitch, can be adjusted in real time, allowing the voice to be customized.
'This is a huge breakthrough,” said Barnier Geerling, CEO of DAISYS. “Up until now, naturally sounding voices were always deepfake, based on audio data of professional speakers. But deepfakes in text-to-speech for many reasons aren’t usable. One of those reasons is that not everyone wishes to lend out their voice without having control about what is being said with it. With this technology, as the first company in the world, we can create new voices that sound like real people.”
“In addition, this technology makes it easier and faster to apply speech-steered technology. The market potential is enormous, think of audio-visual media using voice-overs, or ‘talking’ cars, robots, or appliances. For manufacturers this means the possibility to integrate realistic speech in their products becomes much easier and more efficient,” he added.
During the past year and a half, the start-up from Leiden has worked on its technology with a small international team of AI developers.
“We’ve made several important adjustments to the existing basic technology. In addition, we had to cleverly train our models, using the right balance of speech data from different speakers. Because of this we’ve managed to generate new, naturally sounding voices that can be real-time adjusted by means of gender, pitch, power, and speed,” Dr Joost Broekens, chief technology officer at DAISYS, explained.
The new voice technology is suitable for all online and offline surroundings where the human voice is used, like traditional media, smart devices, games, robots, speech assistants and public announcement systems.
Listen to samples of the new voice technology here: www.daisys.ai.